Incremental Joint Extraction of Entity Mentions and Relations

By Qi Li, Heng Ji. 2014

503 citations recorded by the source corpus.

We present an incremental joint framework to simultaneously extract entity mentions and relations using structured perceptron with efficient beam-search. A segment-based decoder based on the idea of semi-Markov chain is adopted to the new framework as opposed to traditional token-based tagging. In addition, by virtue of the inexact search, we developed a number of new and effective global features as soft constraints to capture the interdependency among entity mentions and relations. Experiments on Automatic Content Extraction (ACE) 1 corpora demonstrate that our joint model significantly outperforms a strong pipelined baseline, which attains better performance than the best-reported end-to-end system.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks (2018, methodology): “Here again, our predictors do not require additional features like dependency trees (Miwa and Bansal 2016) or handengineered heuristics (Li and Ji 2014).”
A neural joint model for entity and relation extraction from biomedical text (2017, background): “For instance, given a sentence “The tire maker still employs 1400” [15], although it may be difficult to recognize “1400” as a person entity, the word “employs” indicates an employment-organization relation which must involve a person entity.”
Modeling Joint Entity and Relation Extraction with Table Representation (2014, background): “Li and Ji (2014) recently proposed a history-based structured learning approach that is simpler and more computationally efﬁcient than other approaches.”
Leveraging Knowledge Bases in LSTMs for Improving Machine Reading (2017, methodology): “We use the same data splits and task settings for ACE2005 as in Li et al. (2014) and for OntoNotes 5.0 as in Durrett and Klein (2014).”
Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction (2019, background): “Li and Ji (2014) deﬁne a global structure for joint entity and relation extraction, encode local and global features based on domain and linguistic knowledge. and leverage beam-search to ﬁnd global optimal assignments for entities and relations.”
Joint Models for Extracting Adverse Drug Events from Biomedical Text (2016, methodology): “…Clark, 2008], NER and parsing [Finkel and Manning, 2009], POS tagging and parsing [Bohnet and Nivre, 2012; Zhang et al., 2012], morphological generation and syntactic linearization [Song et al., 2014], and entity and relation extraction [Roth and Yih, 2007; Chan and Roth, 2011; Li and Ji, 2014].”
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction (2019, methodology): “Joint entity recognition and relation extraction models (Yu and Lam, 2010; Li and Ji, 2014; Miwa and Sasaki, 2014; Ren et al., 2017) have been built to take advantage of the close interaction between these two tasks.”
Entity-Relation Extraction as Multi-Turn Question Answering (2019, methodology): “In later studies, Li and Ji (2014) extract entity mentions and relations us-ing structured perceptron with efﬁcient beam-search, which is signiﬁcantly more efﬁcient and less Time-consuming than constraint-based approaches.”
A general framework for information extraction using dynamic span graphs (2019, background): “3038 domain-specific external syntactic tools to construct dependency paths between the entities in a sentence (Li and Ji, 2014; Xu et al., 2015; Miwa and Bansal, 2016; Zhang et al., 2017).”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, methodology): “…slower than the union of the individual 2 Our model could potentially be extended to handle relation extraction or mention detection, which has also been addressed in past joint modeling efforts (Daum´e and Marcu, 2005; Li and Ji, 2014), but that is outside the scope of the current work. models.”
A language-independent neural network for event detection (2016, background): “(4) Joint Model (Li and Ji, 2014), a joint structured perception approach, incorporating multilevel linguistic features to extract event triggers and arguments at the same time so that local predictions can be mutually improved.”
Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, methodology): “Miwa and Sasaki (2014) and Li and Ji (2014) used approaches motivated by a table-ﬁlling method to jointly extract entity pairs as well as their relations.”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “Early researchers concentrate on intriguing statistical-based features for fast end-to-end joint relation extraction, such as Integer Linear Programming-based (ILP) algorithm [216] solving entities and relations via conditional probabilistic model, semi-Markov chain model [217] jointly decoding glob”
A Frustratingly Easy Approach for Entity and Relation Extraction (2021, methodology): “…dominated by systems 1 Our code and models are publicly available at https: //github.com/princeton-nlp/PURE . that model these two tasks jointly (Li and Ji, 2014; Miwa and Bansal, 2016; Katiyar and Cardie, 2017; Zhang et al., 2017a; Li et al., 2019; Luan et al., 2018, 2019; Wadden et al., 2019;…”